(基于Java)编写编译器和解释器-第5A章:基于Antlr解析表达式和赋值语句及计算(连载)
Posted on 2012-07-22 19:25 Bang 阅读(1129) 评论(1) 编辑 收藏 举报本章在第3A章源代码基础上继续完善基于Antlr自动化的解析器,解释执行第5章解析的复合语句,赋值语句和表达式等相关中间码。并仿照第5章的简化标准,将一些东西简化掉,尽量能让你从最简处入手,掌握Antlr自动化构建解析器的第一步。
==>> 本章中文版源代码下载:svn co http://wci.googlecode.com/svn/branches/ch5_antlr/ 源代码使用了UTF-8编码,下载到本地请修改!
好的工具事半功倍,Antlr亦如此。antlr.org上有一个很有特色的工具antlrwors。如果使用Eclipse,可以安装插件antlrv3ide。两个工具的主要特色是可视化的创建EBNF语法,就如同你在前面章节看到的语法图一样。对于我来说,比较习惯antlrworks,它有良好的调试功能和DFA分析功能。
1 带AST构造的语法
1: program:
2: compound_statement DOT!;
3: compound_statement:
4: BEGIN statement_list END ->^(COMPOUND statement_list);
5: assignment_statement:
6: ID ASSIGN expression -> ^(ASSIGN ID expression);
7: statement:
8: compound_statement | assignment_statement;
9: statement_list:
10: statement (SEMI statement)* SEMI? -> statement+;
11: expression:
12: simple_expression (rel_ops^ simple_expression)?;
13: rel_ops:
14: LT | LE | GT | GE | NOT_EQUAL;
15: simple_expression:
16: signedterm (add_ops^ term)*;
17: signedterm:
18: (a=PLUS | a=MINUS)? term ->{a!=null&&a.getType()==MINUS}?^(NEGATE term)->term;
19: add_ops:
20: PLUS | MINUS | OR;
21: term:
22: factor (mul_ops^ factor)*;
23: mul_ops:
24: STAR | SLASH | DIV | MOD | AND;
25: factor:
26: ID | NUMBER | STRING | NOT^ factor | LPAREN! expression RPAREN!;
目前的程序program由一个复合语句+结束的点"."组成。这个antlr语句基本与第五章的语法图5-1 和图5-2 类似。
2 计算Token值
填充第三章中关于计算常量token的值类ValueComputer,目前只对整数,字符串,浮点数token算值,算值逻辑与PascalStringToken和PascalNumberToken基本类似。
详细参见代码ValueComputer,这里不再显示。
3 引入符号表
这里复用第5章的符号表。需要使用符号表的地方有两个,一个是赋值语句的左边变量作为定义出现,另外一个是表达式中的标识符作为引用出现。在Antlr分析中,一般符号表必须要在语法树构建完成后才能进行,因为语法树构建过程中的节点是不清晰的。在Antlr中构建完AST之后,将使用Antlr树语法(Tree Grammar)去遍历语法,这个过程中我们可以加入符号表操作,也可以执行动作和生成代码。
4 执行赋值语句及计算语句
我原本想只想演示一下相关分析树,但是发现过于简单,于是就干脆执行算了,执行第5章的分析树是第6章内容,所有没有6A章了。
详细语法如下表:
1: tree grammar PascalVisitor;
2: options{
3: tokenVocab=Pascal;
4: ASTLabelType=PascalNode;
5: }
6: @header{
7: package com.lifesting.book.wci;
8:
9: import wci.intermediate.*;
10: import wci.intermediate.symtabimpl.SymTabKeyImpl;
11: }
12: @members{
13: protected SymTabStack symtabStack = SymTabFactory.createSymTabStack();
14: public SymTabStack getSymbolTableStack(){
15: return this.symtabStack;
16: }
17: }
18: program :
19: compound;
20: compound :
21: ^(COMPOUND stmt+);
22: stmt:
23: compound | assign;
24: assign:
25: ^(ASSIGN i=ID e=expr){
26: String var = $i.text.toLowerCase();
27: SymTabEntry id_entry = symtabStack.lookup(var) ;
28: if (id_entry == null)
29: {
30: id_entry = symtabStack.enterLocal(var);
31: }
32: id_entry.setAttribute(SymTabKeyImpl.DATA_VALUE,e);
33: };
34: expr returns[Object value]:
35: s=simple{value=s;}
36: | ^(r=rel_ops e1=expr e2=expr){
37: if (e1 instanceof Number && e2 instanceof Number){
38: double de1 = ((Number)e1).doubleValue();
39: double de2 = ((Number)e2).doubleValue();
40: switch (r){
41: case 1:
42: value = de1 < de2;
43: break;
44: case 2:
45: value = de1 <= de2;
46: break;
47: case 3:
48: value = de1 > de2;
49: break;
50: case 4:
51: value = de1 >= de2;
52: break;
53: case 5:
54: value = de1 != de2;
55: break;
56: default:
57: break;
58: }
59: }else{
60: System.err.println("无法执行比较:"+e1+"["+r+"]"+e2);
61: }
62: };
63: simple returns[Object value]:
64: s=term{value=s;}
65: | ^(o=add_ops f1=negterm f2=simple)
66: {
67: double df1 = Double.parseDouble(f1.toString());
68: if (f2 instanceof Number){
69: double df2 = Double.parseDouble(f2.toString());
70: switch (o)
71: {
72: case 1:
73: value = df1+df2;
74: break;
75: case 2:
76: value = df1-df2;
77: break;
78: }
79: }else{
80: System.err.println("不是一个数值:"+f2);
81: }
82: }
83: | ^(o=add_ops f1=simple f2=simple){
84: if (f1 instanceof Number && f2 instanceof Number){
85: double df1 = Double.parseDouble(f1.toString());
86: double df2 = Double.parseDouble(f2.toString());
87: switch (o){
88: case 1:
89: value = df1+df2;
90: break;
91: case 2:
92: value = df1-df2;
93: break;
94: default:
95: break;
96: }
97: }else if (f1 instanceof Boolean && f2 instanceof Boolean){
98: value= ((Boolean)f1).booleanValue() || ((Boolean)f2).booleanValue();
99: }else{
100: System.err.println("不能执行simple运算,f1="+f1+",f2="+f2);
101: }
102: };
103:
104:
105: negterm returns[Object value]:
106: ^(NEGATE n=term) {
107: if(n instanceof Number){
108: return -Double.parseDouble(n.toString());
109: }else{
110: System.err.println("不是一个数值:"+n);
111: value = 0.0;
112: }
113: };
114:
115: term returns[Object value]:
116: f0=factor{value=f0;}
117: | ^(t=mul_ops f1=factor f2=factor){
118: if (f1 instanceof Number && f2 instanceof Number){
119: double df1 = Double.parseDouble(f1.toString());
120: double df2 = Double.parseDouble(f2.toString());
121: switch (t){
122: case 1:
123: value= df1*df2;
124: break;
125: case 2:
126: case 3:
127: value= df1/df2;
128: case 4:
129: value=df1 \% df2;
130: default:
131: break;
132: }
133: }else if (f1 instanceof Boolean && f2 instanceof Boolean){
134: value= ((Boolean)f1).booleanValue() && ((Boolean)f2).booleanValue();
135: }else{
136: System.err.println("不能执行term运算,f1="+f1+",f2="+f2);
137: }
138: };
139:
140: factor returns[Object value]:
141: i = ID{
142: String var = $i.text.toLowerCase();
143: SymTabEntry id_entry = symtabStack.lookup(var);
144: if (id_entry == null){
145: System.err.println("使用不存在的变量:"+var);
146: }else{
147: value = id_entry.getAttribute(SymTabKeyImpl.DATA_VALUE);
148: }
149: }
150: | n=NUMBER{value =((PascalAntlrToken)$n.getToken()).getValue();}
151: | r=NUMBER_REAL{value = ((PascalAntlrToken)$r.getToken()).getValue();}
152: | s=STRING {value =((PascalAntlrToken)$s.getToken()).getValue(); }
153: | ^(NOT f=factor) {
154: if (f instanceof Boolean){
155: value = !((Boolean)f).booleanValue();
156: }else{
157: System.err.println("不是一个布尔值:"+f);
158: }
159: }
160:
161: | ^(NESTEXPR e = expr){
162: value = e;
163: };
164:
165: rel_ops returns [int type]:
166: LT{type =1;} | LE{type = 2;} | GT{type=3;} | GE{type=4;} | NOT_EQUAL{type=5;};
167: add_ops returns [int type]:
168: PLUS{type=1;} | MINUS{type=2;} | OR{type=3;};
169: mul_ops returns [int type]:
170: STAR{type = 1;} | SLASH{type=2;} | DIV{type=3;} | MOD{type=4;} | AND{type=5;};
测试程序:
1: public final class SimpleInterpreter {
2: public static void main(String[] args) throws IOException, RecognitionException {
3: //第5章示例Pascal
4: InputStreamReader stream = new InputStreamReader(ShowToken.class.getResourceAsStream("/assignments.txt"));
5: ANTLRReaderStream reader = new ANTLRReaderStream(stream);
6: //词法分析器
7: PascalLexer lexer = new PascalLexer(reader);
8: CommonTokenStream token_stream = new CommonTokenStream(lexer);
9: //语法分析器并带自己的TreeAdaptor,转换成自己的PascalNode
10: PascalParser parser = new PascalParser(token_stream);
11: parser.setTreeAdaptor(new PascalNodeAdaptor());
12: program_return prog = parser.program();
13: //遍历树并运算
14: TreeNodeStream node_stream = new CommonTreeNodeStream(prog.getTree());
15: PascalVisitor interpreter = new PascalVisitor(node_stream);
16: interpreter.program();
17: SymTabStack stack = interpreter.getSymbolTableStack();
18: SymTabEntry five_entry = stack.lookup("five");
19: System.out.println("Five = "+five_entry.getAttribute(SymTabKeyImpl.DATA_VALUE));
20: SymTabEntry str_entry = stack.lookup("str");
21: System.out.println("str = "+str_entry.getAttribute(SymTabKeyImpl.DATA_VALUE));
22: SymTabEntry fahrenheit_entry = stack.lookup("fahrenheit");
23: System.out.println("fahrenheit = "+fahrenheit_entry.getAttribute(SymTabKeyImpl.DATA_VALUE));
24: SymTabEntry centigrade_entry = stack.lookup("centigrade");
25: System.out.println("centigrade = "+centigrade_entry.getAttribute(SymTabKeyImpl.DATA_VALUE));
26: }
27: }
最后的输出结果:
Five = 5.0
str = 'hello, world'
fahrenheit = 32.0
centigrade = 25